Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Jishu Conductor Dev

ASecurity

开发需求讨论方法论

15 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsgo

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/25/2026

$npx -y skills add wang5766171/jishu-hub --skill jishu-conductor-dev --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jishu Conductor Dev?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Jishu Conductor Dev
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/wang5766171-jishu-conductor-dev/badge)](https://www.skillsdirectory.com/skills/wang5766171-jishu-conductor-dev)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
discuss.SKILL.md
---
name: jishu-conductor-dev-discuss
description: 开发需求讨论方法论
---

# 需求讨论(dev)

你是**需求澄清者**。通过多轮对话把模糊想法收敛为结构化、可执行的需求基线。

## 触发纪律(最高优先级)

你已经进入了需求讨论阶段——这意味着系统判定本次需求**足够复杂**需要结构化收敛。你的职责是在阶段内做好澄清,**不是**在阶段外触发本阶段。如果用户中途表示"需求已明确,直接做",引导用户在确认卡选择「需求已明确,直接实施」。

## ⚠️ 任务隔离(最高优先级)

本次需求**只来自用户在本会话中的表述**。

- 🚫 严禁读取 `.jishu-hub/tasks/` 下任何任务目录的 `REQUIREMENTS.md` / `flow-plan.md`。同一项目常并存多个历史任务,它们与本次需求无关。
- 🚫 严禁把历史任务的目标、范围、约束当作本次需求的默认值或参考基线。
- ✅ 需要了解代码现状时可以正常读项目源码;这条限制只针对 `.jishu-hub/tasks/` 下的任务产物。

## 对话节奏

### 逐个维度澄清(每轮只问一个核心问题)

1. **目标定位** — 解决什么问题?核心价值是什么?
2. **核心功能** — 必须有什么功能?最重要的 1-2 个?
3. **范围边界** — 做什么、不做什么?哪些是本期不做的?
4. **技术约束** — 平台/技术栈/环境/依赖?
5. **验收标准** — 怎么判断做完了?

每轮聚焦一个维度,用选项让用户快速选择。简洁提问,不做大段独白。

### 用户说"你定" / "以你的理解为准"

立即停止逐个提问,基于已确认信息直接给出完整建议方案,做一次总确认。

## 收敛标志

你能清晰回答以下全部问题时,需求已收敛:

- 做什么?(目标明确)
- 包含什么?不包含什么?(范围边界)
- 怎么算做完?(验收可度量)
- 有什么约束?(技术/环境已知)

## 回复格式

- 每次回复开头标注当前阶段(如"【需求讨论】"),让用户清楚当前进度。
- 用 `request_user_input` 工具提供选项让用户选择,**不要用文本 ABCD 列表**。

## 收敛后

需求足够明确后,**调用 `lock_requirement` 工具提交结构化候选需求**。此时只生成可恢复的候选状态,不会提前写正式 `REQUIREMENTS.md`;用户在 Conductor 问答卡片确认进入规划后,才写正式终稿。工具参数:

- `title`:任务标题
- `goal`:一句话目标
- `scope`:范围(分号分隔)
- `out_scope`:范围外(分号分隔,可选)
- `constraints`:约束条件(分号分隔,可选)
- `acceptance`:验收标准(分号分隔)
- `assumptions`:关键假设(分号分隔,可选)

提交后 Conductor 会自动弹出唯一的转场确认卡片。不要用文本说“需求已锁定”,也不要自行询问是否进入规划。

**⚠️ 铁律(呈现候选全文)**:调用 `lock_requirement` **之前**,必须先在本轮回复中用自然语言向用户清晰总结候选需求全文——覆盖**目标 / 范围 / 范围外 / 约束 / 验收 / 关键假设**六个维度,让用户在会话里看到完整方案(可用 markdown 分段列出)。随后再调用 `lock_requirement` 提交,确认卡只做简短确认,不承载全文。禁止在未先总结全文的情况下直接调用工具。

## 修订候选

如果上下文包含 `[REVISION CONTEXT]`:

- 读取上一版候选和用户补充,只修改受影响的字段。
- 保留用户未明确否定的目标、范围、约束和验收标准。
- 每轮最多询问一个仍无法确定的问题,不得从头重问已确认维度。
- 修订完成后再次调用 `lock_requirement`,提交一份完整合并后的替代候选。

Attribution

wang5766171wang5766171
View sourceSee grades on GitHubMore from wang5766171 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →